Y Combinator Startup Podcast
00:12:24 · Aaron Epstein, Alex Danilowicz
[00:12:24] S0: Cool. So you've got images for Medellin, Singapore. You've got Statue Of Liberty, so New York, and then Toronto. [00:12:31] S1: Exactly. Right. And notice how, like, the agent has all of the context that is on the the canvas already. Right? It automatically knows what is really in the in the file system Mhmm. And what's on this artboard here, and it can go ahead and then make make its updates. So what's cool here is we see it generated all four postcards at once. We can go ahead and just see a bigger version of this here. My prompt was basically telling it to make kind of like a stamp of the the image that that it had. And now we... Because we're on a canvas, I can go ahead and just grab kinda my description of our Singapore event. Right here, I have kinda just some random notes from when our meetup was. It was on May 17. And I can go ahead and select these two. They now make a design of a postcard that references the description thanking users for attending. And when this is done, of course, we can iterate on just the Singapore one specifically, and then apply all of these changes to all the cities at once, right, without having to redo it. [00:13:36] S0: And who are the people, within your team that are actually using this and creating these postcards? Because it seems like it it doesn't necessarily need to be designers. Right?
00:13:36 · Aaron Epstein, Alex Danilowicz
[00:13:36] S0: And who are the people, within your team that are actually using this and creating these postcards? Because it seems like it it doesn't necessarily need to be designers. Right? [00:13:44] S1: Yes. So we have everyone from our ops team to our sales team using Magic Patterns. So as an example, our go to market person is creating these postcards in Magic Patterns to send out to users. And historically, this was someone that didn't know how to use Figma, would have to outsource this type of work. And so that's what's really, I think, special about our our tool is how much we have been kinda democratizing design. [00:14:09] S0: Mhmm. You can export to Figma as well, so you play nicely with the other tools. [00:14:14] S1: One thing that's very different about our tool is that we're model agnostic and, in a way, feature agnostic. Right? Where we encourage folks to export to Figma if they want to and and get high fidelity precision or export to the coding agent of their choice. Right? Some of our other competitors, like Claude Design as an example, it's only the Anthropic models. You're only exporting the Claude Code. There's no integration with Figma. Versus a tool like ours, you know, we have integrations with anything you can think of. [00:14:43] S0: So prompting is obviously very important here. What's your advice for how people should improve their prompts and and get better results from them?
00:14:43 · Aaron Epstein, Alex Danilowicz
[00:14:43] S0: So prompting is obviously very important here. What's your advice for how people should improve their prompts and and get better results from them? [00:14:49] S1: Yeah. I think it's leveraging the features that tools offer. I think it's really interesting that I've seen is there's more and more AI enablement teams popping up with that, especially large companies. And what are they doing? They're leveraging things like skills, agents m d, right, and bringing in your unique context that's relevant to your company. So, of course, we have, you know, skills feature in Magic Patterns where you can go ahead and and add your skills. Or as we were talking about, add your design system and bring in your components. And that's what I always recommend first is, like, spend the ten minutes to bring in your existing context. It'll save you hours in the long run. [00:15:28] S0: Mhmm. What's one of the coolest things that that you've seen created with Magic Patterns? [00:15:32] S1: Yeah. One of the most fun is this Rollercoaster Tycoon theme park. It's like a a chocolate park, which is crazy because when we first started this, you know, you would prompt, a form and it would give you back, like, a drop down. Like, the models were so bad. And now suddenly, you know, we're seeing folks literally bring in... Like, building entire video game experiences. Again, this is not a very common use case, but it's kinda sharing what's possible when the input and output is code. [00:16:01] S0: And what was this created for?
00:16:01 · Aaron Epstein, Alex Danilowicz
[00:16:01] S0: And what was this created for? [00:16:02] S1: This is really just created for fun, you know, experimenting with what is possible, like, in in the browser and actually thinking through how components can help you design in a tool like this. Right? So actually, when you think about a chocolate factory theme park in Roller Coaster Tycoon, the track is a component. The chocolate bar twister ride is a component. The path that guests walk on are components. And so when you give the AI those guardrails, how can it output, like, a theme park in one shot or two shots, bringing in that context? [00:16:38] S0: Mhmm. Very cool. And you can even get right in there. See all the little people walking around. [00:16:42] S1: Yeah. And again, it's amazing. We're like, this is literally just, you know, WebGL rendering in the in the browser. Right? And we can see that we... Again, the way that we did this is we use a design system that we called the 3 D Theme Park. Right? So I can go ahead and update that to bring in my my latest components. And and updating it is really as simple as prompting something like, no trees, just lollipops and more chocolate rivers. Right? Mhmm. [00:17:06] S0: What does this tell you now about what might be possible with Magic Patterns? It seems like this is far beyond just making a postcard or or website design or something.
00:17:06 · Aaron Epstein, Alex Danilowicz, S2
[00:17:06] S0: What does this tell you now about what might be possible with Magic Patterns? It seems like this is far beyond just making a postcard or or website design or something. [00:17:14] S1: Yeah. I think it's showing me that design has historically been two d. Right? And it's been really hard if you worked on a software team four years ago. Going back and forth with the designer and the engineer and the PM, what should the exact interaction be? Then you see something like this where people are, you know, one shotting three d theme parks. And I think it's a taste of the of the future where people can really design full on interactions that are high fidelity, you know, and using their their components. [00:17:43] S0: Yeah. It's gonna be a wild future for sure. Definitely. [00:17:47] S2: YC's next batch is now taking applications. Got a startup in you? Apply at ycombinator.com/apply. It's never too early, and filling out the app will level up your idea. Okay. Back to the video. [00:18:01] S0: You talked about how you've seen thousands of vibe coded designs. You're probably a a world expert on this. Should we review some websites? Let's review some websites. [00:18:09] S1: This will be a lot of fun. [00:18:10] S0: Okay. Great. Alright. First, looks like we got ego. Agents are machines. We make them people. Ego is an applied AI research lab building personal agents indistinguishable from humans. [00:18:22] S1: Okay. [00:18:22] S0: Alright. What do we think?
00:18:22 · Aaron Epstein, Alex Danilowicz
[00:18:22] S0: Alright. What do we think? [00:18:23] S1: So first off, I mean, it's cool. Here's here's the thing that I think people miss about landing pages in general. The real metric to track is does it convert. And I obviously don't know what what it... If this is converting or not. But my sense is, like, I don't know, it's not accessible. I don't know where the CTA is. Is the CTA Ronin? [00:18:44] S0: Yeah. What do what do you think they want us to do here? [00:18:47] S1: I mean, my initial reaction is, like, I should just keep scrolling. Yeah. Right? One interesting thing that we've learned about our own landing page is, you know, everyone that has a vibe coded tool has that input to to prompt to get started. Mhmm. And for a little while, we removed it to try and be more creative. Mhmm. And our conversion rate totally tanked. We learned why people do that. Right? And so I always encourage folks to think about, like, what are you ultimately trying to do here? [00:19:17] S0: Okay. So then there's, like, an app in there. Yeah. I guess I'm halfway down the page, and I'm still unclear what is this and who is it for. I guess there's a wait list, so maybe it's not live yet. [00:19:29] S1: Yeah. Let's